A Performance Evaluation of Classic Convolutional Neural Networks for 2D and 3D Palmprint and Palm Vein Recognition

Palmprint recognition and palm vein recognition are two emerging biometrics technologies. In the past two decades, many traditional methods have been proposed for palmprint recognition and palm vein recognition, and have achieved impressive results. However, the research on deep learning-based palmprint recognition and palm vein recognition is still very preliminary. In this paper, in order to investigate the problem of deep learning based 2D and 3D palmprint recognition and palm vein recognition in-depth, we conduct performance evaluation of seventeen representative and classic convolutional neural networks (CNNs) on one 3D palmprint database, five 2D palmprint databases and two palm vein databases. A lot of experiments have been carried out in the conditions of different network structures, different learning rates, and different numbers of network layers. We have also conducted experiments on both separate data mode and mixed data mode. Experimental results show that these classic CNNs can achieve promising recognition results, and the recognition performance of recently proposed CNNs is better. Particularly, among classic CNNs, one of the recently proposed classic CNNs, i.e., EfficientNet achieves the best recognition accuracy. However, the recognition performance of classic CNNs is still slightly worse than that of some traditional recognition methods.

     

基于Siamese-YOLOv4的印刷品缺陷目标检测

在印刷工业生产中,针对直接使用YOLOv4网络进行印刷缺陷目标检测精度低、所需训练样本数量大的问题,提出了一种基于Siamese-YOLOv4的印刷品缺陷目标检测方法。首先,使用了一种图像分割和随机参数变化的策略对数据集进行增强;然后,在主干网络中增加了孪生相似性检测网络,并在相似性检测网络中引入Mish激活函数来计算出图像块的相似度,在此之后将相似度低于阈值的区域作为缺陷候选区域;最后,训练候选区域图像,从而实现缺陷目标的精确定位与分类。实验结果表明：Siamese-YOLOv4模型的检测精度优于主流的目标检测模型,在印刷缺陷数据集上,Siamese-YOLOv4网络对卫星墨滴缺陷的检测准确率为98.6%,对脏点缺陷的检测准确率为97.8%,对漏印缺陷的检测准确率为93.9%;检测的平均精度均值（mAP）达到了96.8%,相较于YOLOv4算法、Faster R-CNN算法、SSD算法、EfficientDet算法分别提高了6.5个百分点、6.4个百分点、14.9个百分点、10.6个百分点。所提Siamese-YOLOv4模型一方面在印刷品缺陷检测中有较低的误检率和漏检率,另一方面通过相似性检测网络计算图像块的相似度从而提高了检测的精度,表明所提缺陷检测方法可应用于印刷质检以提高印刷企业的缺陷检测水平。     

Improved Computational Model of Grid Cells Based on Column Structure

To simulate the firing pattern of biological grid cells, this paper presents an improved computational model of grid cells based on column structure. In this model, the displacement along different directions is processed by modulus operation, and the obtained remainder is associated with firing rate of grid cell. Compared with the original model, the improved parts include that: the base of modulus operation is changed, and the firing rate in firing field is encoded by Gaussian-like function. Simulation validates that the firing pattern generated by the improved computational model is more consistent with biological characteristic than original model. Besides, the firing pattern is badly influenced by the cumulative positioning error, but the computational model can also generate the regularly hexagonal firing pattern when the real-time positioning results are modified.     

P2P网络中基于RDF/S的数据库语义查询系统设计*

提出一种P2P网络环境下基于RDF/S 数据模型的数据库语义查询原型系统,可以有效地对各种基于ODBC的异构数据源进行语义查询。首先数据内容经RDF/S描述成RDF/S schema片断形式,然后对片段进行编码,再把编码杂凑到DHT中,就可以使用Chord协议定位目标节点。     

时效对接触线用Cu-Ag-Cr合金性能的影响

分析了固溶温度、时效及时效前冷变形量对Cu - 0 1 %Ag - 0 1 %Cr接触线用合金性能的影响 ,结果表明 :经 870℃固溶、 40 %～ 5 0 %冷变形及 480℃× 1 5h时效处理后 ,合金可获得良好的综合性能。     

Ni-Cr-Fe-Si-B合金涂层及铝青铜基体熔合区组织的研究

采用钨极氩弧焊方法在铝青铜基体上施焊了Ni—Cr-Fe-Si—B合金涂层，并运用金相显微镜、扫描电子显微镜及能谱分析了喷涂层、熔合区及热影响区的组织形貌和成分分布。结果表明，喷焊时，在涂层与基体界面两侧各组元均发生了明显的扩散，Cu、Ni组元间可相互取代，基体融合区组织的基本组成仍为α (α γ2)，但同时也形成了Cu2FeAl7、NiAl3等新相，且融合区组织细小，涂层与基体间为冶金态结合。     

基于机会网络中社交关系的转发机制

由于现有的机会网络转发机制不能完全适应社会网络中基于社交关系的判断与分析,为此通过建立社交关系的分类,构建机会网络中的社会关系树结构模型,提出了一种新的转发机制。该机制设置了节点权重值,由节点所处的层次和社会关系的可利用性及可靠性决定。通过路径权重值,选择最有价值的路径进行消息的传递。通过仿真实验,所提出的转发机制有效地降低了网络中的消息副本数和降低了路由开销。     

基于Web的集群管理系统结构

介绍高性能计算集群管理现状, 并根据目前管理缺点与不足, 对集群管理系统进行了总体框架设计, 利用Linux中/proc文件系统、MySQL数据库及Web技术, 对管理数据采集、数据存储及应用接口进行了功能设计, 最终实现了在统一Web界面中对集群系统运行实时情况、历史数据统计与分析进行管理.     

利用标志点多视图约束实现结构光扫描高精度粗拼接

在采用标志点拼接的结构光扫描系统中,两两相邻视图拼接存在累积误差,导致拼接精度会随拼接次数下降,为此提出一种利用标志点多视图几何约束的高精度拼接方法.首先利用两两视图拼接的方式在扫描过程中构建标志点多视图网络,并利用光束法平差技术优化多视图网络得到高精度全局控制点;在此过程中保存每个视局部坐标系下三维点云,然后将各局部坐标系下点云和全局控制点进行拼接,得到物体表面完整的三维数据.该方法克服了传统拼接过程中累积误差,提高了多视角三维扫描拼接精度;并通过实验证明了所提出算法的有效性.     

遥感网格的数据压缩与任务分配方法研究

网格计算作为分布式计算在科学计算领域的发展方向,可以为对地观测数据的处理提供强大的计算力。在分析遥感信息服务网格节点(Remote Sensing Information Service Grid Nodes,RSSN)中网络数据传输和负载均衡两个关键问题的基础上,提出了一种有效的基于游程编码和Huffman编码的数据压缩方法和基于"计算端元"的任务分配策略,该方法针对遥感影像特点进行有效数据压缩,具有较好的压缩比,达到了17%,且能实现任务负载均衡。并在遥感信息服务网格节点计算平台上,以中国范围内1km分辨率气溶胶光学厚度(Aerosol Optical Depth,AOD)反演计算为例,从压缩率和计算时间效率方面验证和分析了上述方法的有效性。